evaluation process is stucked

[SeungHwi0613]

when i learn this torchpack dist-run -np 2 python tools/test.py configs/nuscenes/det/transfusion/secfpn/camera+lidar/swint_v0p075/convfuser.yaml pretrained/bevfusion-det.pth --eval bbox

top_proposals_class = top_proposals // heatmap.shape[-1] [ ] 2/81, 0.5 task/s, elapsed: 4s, ETA: 145s/home/bev/bevfusion/mmdet3d/core/bbox/coders/transfusion_bbox_coder.py:96: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor). self.post_center_range = torch.tensor( [>>] 82/81, 7.9 task/s, elapsed: 10s, ETA: 0s

process is stucked. i use 24+10gb gpu.

plus, when i tried torchpack dist-run -np 2 python tools/test.py configs/nuscenes/det/centerhead/lssfpn/camera/256x704/swint/default.yaml pretrained/camera-only-det.pth --eval bbox

it was working

I want to know the reason of this....

[EpicGilgamesh]

Hi! I see that you got no answers, but I'm fighting with the same issue. How long have you waited to see something happen after mmdet - INFO - load checkpoint from http path: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_tiny_patch4_window7_224.pth ?

[zhijian-liu]

Could you try running the evaluation on a single GPU to see if the same issue still persists? Thank you.